Case study

How Eurofirany turns 1 in 9 chats
into an order

Eurofirany is a Polish home-textiles retailer — net curtains, curtains and Roman blinds, bedding, towels, rugs and cushions — sold online, through its own showrooms across Poland, and made to measure in its own sewing workshop in Żywiec.

4 min read

Eurofirany Assistant
Type your question
Powered by spot

Scale

50+ showrooms · 420,000 visits a month

Platform

Magento

Years on market

35

Results

Key results

Measured in AskSpot across 2,306 chats in a 30-day window. The average chat-driven order is €108 — a pair of curtains and the cushion covers to go with them, rather than one big-ticket item. Both the cart-add rate and the purchase rate are the highest of any merchant we have measured.

€28,000

in chat-driven orders a month

26%

of chats fill a basket

11%

of chats end in a purchase

94%

of chats resolved with no human

Before AskSpot

Every window is a different window

A curtain is not bought the way a lamp is bought. It is bought with a tape measure, and the arithmetic is not obvious: a ready-made panel has to be one and a half to two times the width of the rail or the fabric hangs flat instead of falling in folds. So the shopper standing in front of a 170 cm pole does not know whether to order 140 cm, 350 cm or two of something. Then come the header types — eyelets, tape, tunnel, clip rings, wave — and whether any of them fits the rail already on the wall.

Half of the catalogue makes it harder still, because it is cut and sewn to order in Eurofirany’s own workshop. That is a configuration, not a click: width after gathering, height, fabric, heading, and a swatch in the post before anyone commits. Every one of those questions used to end at a product page that could not answer it, or in an e-mail sent at half past ten at night — which is when two thirds of them are asked.

What decides the sale

centimetres

Where the answer lived

the product page

Made-to-measure enquiry

phone or e-mail

Help after closing

none

Rollout

How they rolled it out

One module, three jobs, in the order a window purchase actually happens: get the measurement right, turn it into a workshop order, then furnish the rest of the room.

AI Sales Agent

Step 01

Catalogue & Size Grounding

Answering with the tape measure out

The 12,700-product Magento catalogue was indexed on the numbers that decide a window purchase — panel width and drop, gathering ratio, header type, fabric weight, how much light it stops — so the agent can turn “my rail is 170 cm” into a width rather than a category page.

What shoppers ask

  • My rail is 170 cm — how much net curtain do I need?
  • Is the stated width before or after gathering?
  • How wide should blackout curtains be for a 140 cm window?

AI Sales Agent

Step 02

Made-to-Measure Configuration

The workshop order, taken in chat

The sewing workshop in Żywiec was given its own rules in the agent: dimensions are quoted as width after gathering, the lead time is 7–9 working days, and a fabric swatch can be ordered from the product page before anything is cut.

What shoppers ask

  • Can this be made up 215 by 269 cm?
  • Can you narrow a curtain from 140 cm to 100 cm?
  • Do you send fabric samples?

AI Sales Agent

Step 03

Matching Across the Room

The second half of the sale

Cushion covers, tiebacks, bedding, towels and rugs were mapped to the fabrics and shades they share, so “match these to the curtains in my basket” returns products rather than a category. 62% of the recommendations the agent puts up get clicked.

What shoppers ask

  • Find cushion covers to go with the curtains in my basket
  • Which towels go with the Jessi bath mat?
  • A Roman blind in the same fabric as the ZOEY curtain

Measured in AskSpot

What the agent does in a month

62%

product recommendation click-through

2,306

conversations handled a month

64%

of chats come in after hours

6 s

average first response

From real conversations

What Eurofirany shoppers actually ask

Nearly three quarters of everything asked is one shopper doing one job: picking the right thing and checking it will fit. "Which of these should I buy?" leads, and "what exactly are the dimensions?" comes straight after it — because a ready-made curtain has to be one and a half to two times the width of the rail, and almost nobody knows that. Order status is 2.6%. This is a selling desk, not a support desk.

Finding the right product43.4%
Specs, materials & sizes29.3%
Delivery & buying terms9.4%
Discounts & promotions5.6%
Availability & restock5.3%
Accessories & spare parts3.6%
Fit & compatibility3.4%
Returns & complaints2.7%
Order status & changes2.6%

Based on 2,306 tagged conversations over 30 days · about 9 messages each · 64% arriving outside business hours.

More case studies

See how other stores use AskSpot

More stories from teams that automate support and grow sales with AskSpot.

All case studies

Twoje Meble

How Twoje Meble fills 1 in 5 furniture carts

Twoje Meble's AI sales agent adds an item to the cart in 18.5% of chats and resolves 88% with no human — 2,057 furniture conversations a month, 41% of them after the showroom closes.

Read the story →

Moderno

How Moderno resolves 86% of furniture chats with no human

Moderno's AskSpot chat agent resolves 86% of furniture questions with no human — delivery timing, sizing, stock and order changes — and turns 12% of chats into cart-adds. 1,305 conversations a month, over a third after hours.

Read the story →

Edinos

How Edinos resolves 87% of furniture chats with no human

Edinos' AskSpot agent answers furniture fit, colour and delivery across 35,818 products — 87% of chats resolved with no human, 15% add to cart, 58% CTR.

Read the story →

Morele.net

How Morele.net cut customer service costs by 90%

Morele.net cut customer service costs by 90% and went from 50 support agents to 5. AskSpot resolves 71% of its 37,600 monthly chats with no human, and answers Allegro marketplace questions from the same catalog.

Read the story →

Militaria.pl

How Militaria resolves 83% of chats in 9 languages

Militaria.pl runs AskSpot AI chat across three domains in nine shopper languages: 48% product recommendation click-through, 27% add-to-cart after a chat and 83% of chats resolved with no human — 16,600 conversations a month, over half after hours.

Read the story →

4FIZJO

How 4FIZJO automated 50% of customer inquiries with AI

4FIZJO cut website calls and messages by 40% and automates a third of its helpdesk tickets. AskSpot's AI Chat resolves 74% of its 21,360 monthly chats with no human, across 6 markets, and its Inbox Agent clears email and Allegro tickets in Thulium.

Read the story →

25case studies

See every story

Every merchant we have measured — what shoppers asked, what the agent did, and the numbers it moved.

Browse them all →

Test before you trust

Worried AI will cost you customers?

You never flip a switch and hope. Every answer is checked by our AI, our specialists and your own team before launch — and if you want extra reassurance, you can go live after hours first.

Layer 01

Self-testing AI

Every reply is checked automatically against your catalog and your rules, so off-topic or off-brand answers are caught before anyone sees them.

Layer 02

Vetted by experts

Our specialists challenge it with all kinds of questions, drawing on experience from dozens of e-commerce projects we've run, then sign off on the quality.

Layer 03

Tested on staging

Your own managers get a private staging environment to try the chat end to end — ask anything, push the hardest cases — and approve it before go-live.

Layer 04

After-hours launch

Want extra reassurance? Optionally go live only outside working hours at first, review every answer and the full statistics, then expand when you're ready.

You decide when — and if — AskSpot goes live.
No leap of faith, no lock-in.

Ready to make every conversation sell?

Book a demo and see AskSpot on your own catalog. Onboarding takes a few days.